EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Evaluation of the impact different colour maps have on the efficiency of an ImageNet pre-trained ResNet as an audio feature extractor on DCASE 2018’s domestic activity classification task. All results are given in macro average F1

From: Towards cross-modal pre-training and learning tempo-spatial characteristics for audio recognition with convolutional and recurrent neural networks

Network	Pre-training	Colour map	Devel	Test
ResNet	ImageNet	Cividis	82.6	80.2
ResNet	ImageNet	Gray	82.2	79.4
ResNet	ImageNet	Hot	82.0	79.8
ResNet	ImageNet	Magma	81.9	80.3
ResNet	ImageNet	Viridis	81.2	79.9

Back to article page